
|
|
|
|
| 635 podcasts | 77269 episodes (2110 have been corrected) |
473305 corrected words (Edits) |
PodCastle is a service that enables searching of speech data (podcasts). Speech data are converted to text data by using automatic speech recognition technology. All users accessing the PodCastle service can correct the recognition errors. For more information, please check "What is PodCastle?".
IE8 is now supported.
Please refer to "To podcasters" for the details about how to register a podcast and how to delete a podcast on PodCastle.
Since this beta service is under development, it may suddenly down for maintenance. The transcripts generated by speech recognizer are not necessarily perfect. Recognition errors tend to increase for the podcasts which have bad acoustic conditions (background noises, multiple speakers, spontaneous speeches, etc.).
The following environment is supported by PodCastle.